Journal Papers Applying Neural Networks to Seismology, 1988-2022

637 journal papers from January 1988 to January 2022 applying neural networks to seismological tasks. The dataset, created by S. Mostafa Mousavi of Stanford University, provides a hierarchical classification of papers and includes details on methods, architectures, data, and performance metrics for each paper.

Use Cases

• Literature review and trend analysis based on publication year, journal, and machine learning method fields.
• Benchmarking neural network architectures for specific seismological tasks based on the task classification and performance scores.
• Identifying common data types and training practices in the field based on input data, data domain, and training set type fields.

Strengths

• Covers 637 papers spanning 34 years (1988-2022), providing a long-term view of the field's evolution.
• Includes 18 structured fields per paper, such as neural network architecture, training process, and performance metrics.
• Follows a hierarchical classification system for seismological tasks, aiding in systematic analysis.

Limitations

• Row count for the dataset itself is unknown, which may limit suitability assessment for large-scale analysis.
• Column-level documentation is absent; field semantics must be inferred from the description after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

paperswithcode

Collection Method

Curated collection of published journal papers.

Time Range

January 1988 to January 2022